执行者

执行火炬

ExecuTorch是一种端到端解决方案，用于跨移动和边缘设备（包括可穿戴设备、嵌入式设备和微控制器）实现设备上推理功能。它是 PyTorch Edge 生态系统的一部分，支持将 PyTorch 模型高效部署到边缘设备。

ExecuTorch 的主要价值主张是：

• 便携性：与各种计算平台兼容，从高端移动电话到高度受限的嵌入式系统和微控制器。
• 生产力：使开发人员能够使用相同的工具链和开发人员工具，从 PyTorch 模型创作和转换，到调试和部署到各种平台。
• 性能：由于轻量级运行时间并利用 CPU、NPU 和 DSP 等完整硬件功能，为最终用户提供无缝的高性能体验。

有关 ExecuTorch 的全面技术概述和分步教程，请访问我们的文档网站以获取最新版本（或主分支）。

查看入门页面以快速浏览。

查看使用 ExecuTorch 在边缘设备上运行的 Llama、Llava 和其他模型的示例。

[更新 - 10/24]我们添加了对通过 ExecuTorch 运行 Llama 3.2 量化 1B/3B 模型的支持。

反馈

我们欢迎来自社区的任何反馈、建议和错误报告，以帮助我们改进技术。请使用 PyTorch 论坛进行有关使用ExecuTorch类别的 ExecuTorch 的讨论和反馈，并使用我们的 GitHub 存储库进行错误报告。

我们建议在开发时使用发布页面中的最新版本标签。

贡献

有关问题、PR、代码风格、CI 作业和其他开发主题的详细信息，请参阅 CONTRIBUTING.md。

为了与我们和其他社区成员联系，我们邀请您填写此表格加入 PyTorch Slack 社区。加入后，您可以：

• 前往#executorch-general频道了解一般问题、讨论和社区支持。
• 如果您有兴趣直接为项目开发做出贡献，请加入#executorch-contributors频道​​。

目录结构

 executorch
├── backends                        #  Backend delegate implementations.
├── build                           #  Utilities for managing the build system.
├── codegen                         #  Tooling to autogenerate bindings between kernels and the runtime.
├── configurations
├── docs                            #  Static docs tooling.
├── examples                        #  Examples of various user flows, such as model export, delegates, and runtime execution.
├── exir                            #  Ahead-of-time library: model capture and lowering APIs.
|   ├── _serialize                  #  Serialize final export artifact.
|   ├── backend                     #  Backend delegate ahead of time APIs
|   ├── capture                     #  Program capture.
|   ├── dialects                    #  Op sets for various dialects in the export process.
|   ├── emit                        #  Conversion from ExportedProgram to ExecuTorch execution instructions.
|   ├── operator                    #  Operator node manipulation utilities.
|   ├── passes                      #  Built-in compiler passes.
|   ├── program                     #  Export artifacts.
|   ├── serde                       #  Graph module
serialization/deserialization.
|   ├── verification                #  IR verification.
├── extension                       #  Extensions built on top of the runtime.
|   ├── android                     #  ExecuTorch wrappers for Android apps.
|   ├── apple                       #  ExecuTorch wrappers for iOS apps.
|   ├── aten_util                   #  Converts to and from PyTorch ATen types.
|   ├── data_loader                 #  1st party data loader implementations.
|   ├── evalue_util                 #  Helpers for working with EValue objects.
|   ├── gguf_util                   #  Tools to convert from the GGUF format.
|   ├── kernel_util                 #  Helpers for registering kernels.
|   ├── memory_allocator            #  1st party memory allocator implementations.
|   ├── module                      #  A simplified C++ wrapper for the runtime.
|   ├── parallel                    #  C++ threadpool integration.
|   ├── pybindings                  #  Python API for executorch runtime.
|   ├── pytree                      #  C++ and Python flattening and unflattening lib for pytrees.
|   ├── runner_util                 #  Helpers for writing C++ PTE-execution
tools.
|   ├── testing_util                #  Helpers for writing C++ tests.
|   ├── training                    #  Experimental libraries for on-device training
├── kernels                         #  1st party kernel implementations.
|   ├── aten
|   ├── optimized
|   ├── portable                    #  Reference implementations of ATen operators.
|   ├── prim_ops                    #  Special ops used in executorch runtime for control flow and symbolic primitives.
|   ├── quantized
├── profiler                        #  Utilities for profiling runtime execution.
├── runtime                         #  Core C++ runtime.
|   ├── backend                     #  Backend delegate runtime APIs.
|   ├── core                        #  Core structures used across all levels of the runtime.
|   ├── executor                    #  Model loading, initialization, and execution.
|   ├── kernel                      #  Kernel registration and management.
|   ├── platform                    #  Layer between architecture specific code and portable C++.
├── schema                          #  ExecuTorch PTE file format flatbuffer
schemas.
├── scripts                         #  Utility scripts for size management, dependency management, etc.
├── devtools                        #  Model profiling, debugging, and introspection.
├── shim                            #  Compatibility layer between OSS and Internal builds
├── test                            #  Broad scoped end-to-end tests.
├── third-party                     #  Third-party dependencies.
├── util                            #  Various helpers and scripts.

执照

ExecuTorch 已获得 BSD 许可，如 LICENSE 文件中所示。